High-Dimensional Convolutional Networks for Geometric Pattern Recognition
Abstract
High-dimensional geometric patterns appear in many computer vision problems. In this work, we present high-dimensional convolutional networks for geometric pattern recognition problems that arise in 2D and 3D registration problems. We first propose high-dimensional convolutional networks from 4 to 32 dimensions and analyze the geometric pattern recognition capacity in high-dimensional linear regression problems. Next, we show that the 3D correspondences form hyper-surface in a 6-dimensional space and validate our network on 3D registration problems. Finally, we use image correspondences, which form a 4-dimensional hyper-conic section, and show that the high-dimensional convolutional networks are on par with many state-of-the-art multi-layered perceptrons.
Cite
Text
Choy et al. "High-Dimensional Convolutional Networks for Geometric Pattern Recognition." Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, 2020. doi:10.1109/CVPR42600.2020.01124Markdown
[Choy et al. "High-Dimensional Convolutional Networks for Geometric Pattern Recognition." Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, 2020.](https://mlanthology.org/cvpr/2020/choy2020cvpr-highdimensional/) doi:10.1109/CVPR42600.2020.01124BibTeX
@inproceedings{choy2020cvpr-highdimensional,
title = {{High-Dimensional Convolutional Networks for Geometric Pattern Recognition}},
author = {Choy, Christopher and Lee, Junha and Ranftl, Rene and Park, Jaesik and Koltun, Vladlen},
booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition},
year = {2020},
doi = {10.1109/CVPR42600.2020.01124},
url = {https://mlanthology.org/cvpr/2020/choy2020cvpr-highdimensional/}
}